teams
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes user-supplied problem descriptions which are subsequently passed to sub-agents, creating an indirect injection surface. This is a functional design for task delegation.
- Ingestion points: The
{문제 설명}input in the/teamscommand. - Boundary markers: Absent in the skill instructions.
- Capability inventory: Uses internal tools such as
TeamCreate,Task tool, andSendMessageto manage agents. - Sanitization: Relies on the host system's existing safety protocols.
- [Remote Code Execution] (SAFE): No remote downloads or unauthorized command executions were found. The tool uses internal orchestration capabilities.
Audit Metadata